aceCURL-AID: Automated Echocardiographic Motion Analysis for Quantitative Assessment of Posterior Systolic Curling
Abstract: Objective Posterior systolic curling (PSC) is a morphofunctional abnormality of the posterior mitral annulus associated with malignant ventricular arrhythmias and sudden cardiac death. Current diagnosis is qualitative and operator-dependent, limiting reproducibility, objectivity and standardization. This study introduces CURL-AID (Curling Ultrasound-based Recognition and Labeling-Automated Intelligence-driven Diagnosis), a fully automated echocardiographic framework for PSC detection through quantitative analysi…
"Parasternal Long Axis RV Inflow Schematic" by The original uploader was Michael.veltman at English Wikipedia. is licensed under CC BY 3.0. To view a copy of this license, visit https://creativecommons.org/licenses/by/3.0/.
On 2026-08-12, a peer-reviewed study described CURL-AID, a fully automated framework that segments the posterior mitral annulus and left ventricular wall on parasternal long-axis echocardiograms, tracks tissue motion, and classifies posterior systolic curling using nine kinematic features in 100 retrospectively analyzed patients.
Posterior systolic curling is linked to arrhythmic risk but currently diagnosed qualitatively, so a reproducible quantitative tool could improve standardization and risk stratification; uncertainty remains because performance was measured only with internal nested cross-validation on a single view and single-center retrospective cohort without prospective or external validation.
- Study analyzed 100 patients (40 PSC, 60 noPSC) classified by three independent clinicians based on dynamic visual assessment.
- Pipeline combined convolutional neural network segmentation, point-wise tissue tracking, and nine selected kinematic features reflecting increased tangential and radial displacement.
- Best model was linear support vector machine evaluated with repeated, stratified nested cross-validation.
CURL-AID automated analysis of parasternal long-axis echocardiograms quantified posterior annular hypermobility and classified posterior systolic curling with AUC 0.865 and accuracy 0.82.
The rundown
Researchers developed CURL-AID to replace qualitative operator-dependent visual assessment of posterior systolic curling with automated segmentation of the posterior wall and annulus and point-wise motion tracking from parasternal long-axis views.
From 100 cases, bootstrapped Elastic Net and Sequential Backward Selection identified nine motion descriptors showing increased displacement and irregular systolic acceleration in PSC, yielding median Dice 0.88 for wall segmentation and centroid errors of 2.0 mm validation and 1.6 mm test for annulus localization.
Sources
- Peer-reviewedUltrasound in Medicine & Biology2026-08-12
How should this claim be treated?
The debate